Hugging Face's logo

ICB-UMA
/
ClinLinker

PyTorch
Spanish
roberta
medical
spanish
bi-encoder
entity-linking
sapbert
umls
snomed-ct
Model card Files Community
fernandogd97 commited on
Commit
8be3ce7
·
verified ·
1 Parent(s): ad52637

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -26,7 +26,7 @@ ClinLinker is a state-of-the-art bi-encoder model for medical entity linking (ME
26
  - **Evaluated On**: DisTEMIST, MedProcNER, SympTEMIST
27
  - **Users**: Researchers and practitioners working in clinical NLP
28
 
29
- ## Performance Summary (Top-25 Accuracy)
30
 
31
  | Model | DisTEMIST | MedProcNER | SympTEMIST |
32
  |--------------------|-----------|------------|------------|
@@ -57,7 +57,7 @@ print(embedding.shape)
57
 
58
  For scalable retrieval, use [Faiss](https://github.com/facebookresearch/faiss) or the [`FaissEncoder`](https://github.com/ICB-UMA/KnowledgeGraph) class.
59
 
60
- ## Limitations
61
  - The model is optimized for Spanish clinical data and may underperform outside this domain.
62
  - Expert validation is advised in critical applications.
63
 
 
26
  - **Evaluated On**: DisTEMIST, MedProcNER, SympTEMIST
27
  - **Users**: Researchers and practitioners working in clinical NLP
28
 
29
+ ## 📈 Performance Summary (Top-25 Accuracy)
30
 
31
  | Model | DisTEMIST | MedProcNER | SympTEMIST |
32
  |--------------------|-----------|------------|------------|
 
57
 
58
  For scalable retrieval, use [Faiss](https://github.com/facebookresearch/faiss) or the [`FaissEncoder`](https://github.com/ICB-UMA/KnowledgeGraph) class.
59
 
60
+ ## ⚠️ Limitations
61
  - The model is optimized for Spanish clinical data and may underperform outside this domain.
62
  - Expert validation is advised in critical applications.
63